检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

12,844 篇 会议
13 篇 期刊文献
2 册 图书

馆藏范围

12,859 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

7,573 篇 工学
- 6,863 篇 计算机科学与技术...
- 880 篇 机械工程
- 814 篇 软件工程
- 435 篇 控制科学与工程
- 360 篇 光学工程
- 306 篇 电气工程
- 209 篇 仪器科学与技术
- 124 篇 信息与通信工程
- 91 篇 生物工程
- 62 篇 生物医学工程（可授...
- 39 篇 电子科学与技术（可...
- 34 篇 安全科学与工程
- 26 篇 化学工程与技术
- 21 篇 交通运输工程
- 20 篇 建筑学
- 18 篇 土木工程
2,957 篇 医学
- 2,956 篇 临床医学
- 15 篇 基础医学(可授医学...
- 12 篇 药学(可授医学、理...
700 篇 理学
- 359 篇 物理学
- 225 篇 数学
- 175 篇 系统科学
- 95 篇 统计学（可授理学、...
- 93 篇 生物学
- 22 篇 化学
201 篇 艺术学
- 201 篇 设计学（可授艺术学...
84 篇 管理学
- 59 篇 图书情报与档案管...
- 25 篇 管理科学与工程(可...
- 14 篇 工商管理
23 篇 法学
- 21 篇 社会学
5 篇 农学
4 篇 教育学
2 篇 经济学
1 篇 军事学

主题

6,464 篇 computer vision
2,688 篇 training
2,437 篇 pattern recognit...
1,780 篇 computational mo...
1,522 篇 visualization
1,348 篇 three-dimensiona...
1,091 篇 computer archite...
1,063 篇 semantics
997 篇 benchmark testin...
976 篇 codes
970 篇 conferences
854 篇 feature extracti...
830 篇 cameras
771 篇 task analysis
707 篇 deep learning
646 篇 image segmentati...
611 篇 object detection
595 篇 shape
554 篇 transformers
538 篇 neural networks

机构

132 篇 univ sci & techn...
122 篇 carnegie mellon ...
120 篇 tsinghua univ pe...
114 篇 univ chinese aca...
113 篇 chinese univ hon...
94 篇 tsinghua univers...
91 篇 zhejiang univ pe...
91 篇 swiss fed inst t...
85 篇 peng cheng lab p...
81 篇 university of ch...
80 篇 zhejiang univers...
77 篇 shanghai ai lab ...
77 篇 peng cheng labor...
75 篇 university of sc...
69 篇 shanghai jiao to...
68 篇 shanghai jiao to...
67 篇 alibaba grp peop...
67 篇 stanford univ st...
66 篇 univ hong kong p...
64 篇 sensetime res pe...

作者

77 篇 timofte radu
63 篇 van gool luc
45 篇 zhang lei
36 篇 yang yi
36 篇 luc van gool
34 篇 tao dacheng
31 篇 loy chen change
29 篇 chen chen
28 篇 sun jian
28 篇 qi tian
25 篇 li xin
24 篇 liu yang
24 篇 tian qi
24 篇 ying shan
23 篇 wang xinchao
23 篇 zha zheng-jun
23 篇 boxin shi
21 篇 zhou jie
21 篇 vasconcelos nuno
20 篇 luo ping

语言

12,851 篇 英文
7 篇 其他
1 篇 中文

检索条件"任意字段=IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops"

共 12859 条记录，以下是321-330 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

ViTamin: Designing Scalable vision Models in the vision-Language Era

ViTamin: Designing Scalable Vision Models in the Vision-Lang...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Chen, Jieneng Yu, Qihang Shen, Xiaohui Yuille, Alan Chen, Liang-Chieh Johns Hopkins Univ Baltimore MD 21218 USA ByteDance Beijing Peoples R China

ISBN: (纸本)9798350353006

Recent breakthroughs in vision-language models (VLMs) start a new page in the vision community. The VLMs provide stronger and more generalizable feature embeddings compared to those from ImageNet-pretrained models, thanks to the training on the large-scale Internet image-text pairs. However, despite the amazing achievement from the VLMs, vanilla vision Transformers (ViTs) remain the default choice for the image encoder. Although pure transformer proves its effectiveness in the text encoding area, it remains questionable whether it is also the case for image encoding, especially considering that various types of networks are proposed on the ImageNet benchmark, which, unfortunately, are rarely studied in VLMs. Due to small data/model scale, the original conclusions of model design on ImageNet can be limited and biased. In this paper, we aim at building an evaluation protocol of vision models in the vision-language era under the contrastive language-image pretraining (CLIP) framework. We provide a comprehensive way to benchmark different vision models, covering their zero-shot performance and scalability in both model and training data sizes. To this end, we introduce ViTamin, a new vision models tailored for VLMs. ViTamin-L significantly outperforms ViT-L by 2.0% ImageNet zero-shot accuracy, when using the same publicly available DataComp-1B dataset and the same OpenCLIP training scheme. ViTamin-L presents promising results on 60 diverse benchmarks, including classification, retrieval, open-vocabulary detection and segmentation, and large multi-modal models. When further scaling up the model size, our ViTamin-XL with only 436M parameters attains 82.9% ImageNet zero-shot accuracy, surpassing 82.0% achieved by EVA-E that has ten times more parameters (4.4B).

关键词： Architectural Design vision-Language Models

来源：评论

学校读者我要写书评

暂无评论

Domain Prompt Learning with Quaternion Networks

Domain Prompt Learning with Quaternion Networks

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Cao, Qinglong Xu, Zhengqin Chen, Yuntian Ma, Chao Yang, Xiaokang Shanghai Jiao Tong Univ AI Inst MoE Key Lab Artificial Intelligence Shanghai Peoples R China Eastern Inst Technol Ningbo Inst Digital Twin Ningbo Peoples R China

ISBN: (纸本)9798350353006

Prompt learning has emerged as a potent and resource-efficient technique in large vision-Language Models (VLMs). However, its application in adapting VLMs to specialized domains like remote sensing and medical imaging, termed domain prompt learning, remains relatively unexplored. Although large-scale domain-specific foundation models offer a potential solution, their focus on a singular vision level presents challenges in prompting both vision and language modalities. To address this limitation, we propose leveraging domain-specific knowledge from these foundation models to transfer the robust recognition abilities of VLMs from generalized to specialized domains, employing quaternion networks. Our method entails utilizing domain-specific vision features from domain-specific foundation models to guide the transformation of generalized contextual embeddings from the language branch into a specialized space within quaternion networks. Furthermore, we introduce a hierarchical approach that derives vision prompt features by analyzing intermodal relationships between hierarchical language prompt features and domain-specific vision features. Through this mechanism, quaternion networks can effectively explore intermodal relationships in specific domains, facilitating domain-specific vision-language contrastive learning. Extensive experiments conducted on domain-specific datasets demonstrate that our proposed method achieves new state-of-the-art results in prompt learning. Codes are available at https://***/caoql98/DPLQ.

关键词： domain prompt learning quaternion networks vision-language models

来源：评论

学校读者我要写书评

暂无评论

Part-aware Unified Representation of Language and Skeleton for Zero-shot Action recognition

Part-aware Unified Representation of Language and Skeleton f...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Zhu, Anqi Ke, Qiuhong Gong, Mingming Bailey, James Univ Melbourne Melbourne Vic Australia Monash Univ Parkville Vic 3052 Australia Wellington Rd Clayton Vic 3800 Australia

ISBN: (纸本)9798350353006

While remarkable progress has been made on supervised skeleton-based action recognition, the challenge of zero-shot recognition remains relatively unexplored. In this paper, we argue that relying solely on aligning label-level semantics and global skeleton features is insufficient to effectively transfer locally consistent visual knowledge from seen to unseen classes. To address this limitation, we introduce Part-aware Unified Representation between Language and Skeleton (PURLS) to explore visual-semantic alignment at both local and global scales. PURLS introduces a new prompting module and a novel partitioning module to generate aligned textual and visual representations across different levels. The former leverages a pre-trained GPT-3 to infer refined descriptions of the global and local (body-part-based and temporal-interval-based) movements from the original action labels. The latter employs an adaptive sampling strategy to group visual features from all body joint movements that are semantically relevant to a given description. Our approach is evaluated on various skeleton/language backbones and three large-scale datasets, i.e., NTU-RGB+D 60, NTU-RGB+D 120, and a newly curated dataset Kinetics-skeleton 200. The results showcase the universality and superior performance of PURLS, surpassing prior skeleton-based solutions and standard baselines from other domains. The source codes can be accessed at https://***/azzh1/PURLS.

关键词： action recognition computer vision contrastive learning large language model representation learning skeleton action recognition zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

PoNQ: a Neural QEM-based Mesh Representation

PoNQ: a Neural QEM-based Mesh Representation

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Maruani, Nissim Ovsjanikov, Maks Alliez, Pierre Desbrun, Mathieu Univ Cote Azur INRIA Nice France IP Paris Ecole Polytech LIX Paris France Ecole Polytech Inria Saclay Paris France

ISBN: (纸本)9798350353013;9798350353006

Although polygon meshes have been a standard representation in geometry processing, their irregular and combinatorial nature hinders their suitability for learning-based applications. In this work, we introduce a novel learnable mesh representation through a set of local 3D sample Points and their associated Normals and Quadric error metrics (QEM) w.r.t. the underlying shape, which we denote PoNQ. A global mesh is directly derived from PoNQ by efficiently leveraging the knowledge of the local quadric errors. Besides marking the first use of QEM within a neural shape representation, our contribution guarantees both topological and geometrical properties by ensuring that a PoNQ mesh does not self-intersect and is always the boundary of a volume. Notably, our representation does not rely on a regular grid, is supervised directly by the target surface alone, and also handles open surfaces with boundaries and/or sharp features. We demonstrate the efficacy of PoNQ through a learning-based mesh prediction from SDF grids and show that our method surpasses recent state-of-the-art techniques in terms of both surface and edge-based metrics.

关键词： 3D Mesh Computational Geometry computer vision

来源：评论

学校读者我要写书评

暂无评论

ViT-CoMer: vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions

ViT-CoMer: Vision Transformer with Convolutional Multi-scale...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Xia, Chunlong Wang, Xinliang Lv, Feng Hao, Xin Shi, Yifeng Baidu Inc Beijing Peoples R China

ISBN: (纸本)9798350353013;9798350353006

Although vision Transformer (ViT) has achieved significant success in computer vision, it does not perform well in dense prediction tasks due to the lack of inner-patch information interaction and the limited diversity of feature scale. Most existing studies are devoted to designing vision-specific transformers to solve the above problems, which introduce additional pre-training costs. Therefore, we present a plain, pre-training-free, and feature-enhanced ViT back-bone with Convolutional Multi-scale feature interaction, named ViT-CoMer, which facilitates bidirectional interaction between CNN and transformer. Compared to the state-of-the-art, ViT-CoMer has the following advantages: (1) We inject spatial pyramid multi-receptive field convolutional features into the ViT architecture, which effectively alleviates the problems of limited local information interaction and single-feature representation in ViT. (2) We propose a simple and efficient CNN-Transformer bidirectional fusion interaction module that performs multi-scale fusion across hierarchical features, which is beneficial for handling dense prediction tasks. (3) We evaluate the performance of ViT-CoMer across various dense prediction tasks, different frameworks, and multiple advanced pre-training. Notably, our ViT-CoMer-L achieves 64.3% AP on COCO val2017 without extra training data, and 62.1% mIoU on ADE20K val, both of which are comparable to state-of-the-art methods. We hope ViT-CoMer can serve as a new backbone for dense prediction tasks to facilitate future research. The code will be released at https://***/Traffic-X/ViT-CoMer.

关键词： DensePrediction visionFoundationBackbone visionTransformer

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Hallucination Control by Visual Information Grounding

Multi-Modal Hallucination Control by Visual Information Grou...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Favero, Alessandro Zancato, Luca Trager, Matthew Choudhary, Siddharth Perera, Pramuditha Achille, Alessandro Swaminathan, Ashwin Soatto, Stefano AWS AI Labs Lausanne Switzerland

ISBN: (纸本)9798350353006

Generative vision-Language Models (VLMs) are prone to generate plausible-sounding textual answers that, however, are not always grounded in the input image. We investigate this phenomenon, usually referred to as "hallucination" and show that it stems from an excessive reliance on the language prior. In particular, we show that as more tokens are generated, the reliance on the visual prompt decreases, and this behavior strongly correlates with the emergence of hallucinations. To reduce hallucinations, we introduce Multi-Modal Mutual-Information Decoding (M3ID), a new sampling method for prompt amplification. M3ID amplifies the influence of the reference image over the language prior, hence favoring the generation of tokens with higher mutual information with the visual prompt. M3ID can be applied to any pre-trained autoregressive VLM at inference time without necessitating further training and with minimal computational overhead. If training is an option, we show that M3ID can be paired with Direct Preference Optimization ( DPO) to improve the model's reliance on the prompt image without requiring any labels. Our empirical findings show that our algorithms maintain the fluency and linguistic capabilities of pre-trained VLMs while reducing hallucinations by mitigating visually ungrounded answers. Specifically, for the LLaVA 13B model, M3ID and M3ID+DPO reduce the percentage of hallucinated objects in captioning tasks by 25% and 28%, respectively, and improve the accuracy on VQA benchmarks such as POPE by 21% and 24%.

关键词： language reasoning vision

来源：评论

学校读者我要写书评

暂无评论

Low-Rank Adaptation vs. Fine-Tuning for Handwritten Text recognition

Low-Rank Adaptation vs. Fine-Tuning for Handwritten Text Rec...

引用

2025 ieee/cvf Winter conference on Applications of computer vision workshops, WACVW 2025

作者： Huttner, Lukas Mayr, Martin Gorges, Thomas Wu, Fei Seuret, Mathias Maier, Andreas Christlein, Vincent Friedrich-Alexander Universität Erlangen-Nürnberg Pattern Recognition Lab Erlangen91058 Germany

ISBN: (纸本)9798331536626

The continuous expansion of neural network sizes is a notable trend in machine learning, with transformer models exceeding 20 billion parameters in computer vision. This growth comes with rising demands for computational resources and large-scale datasets. Efficient techniques for transfer learning thus become an attractive option in setups with limited data, as in handwriting recognition. Recently, parameter-efficient fine-tuning (PEFT) methods, such as low-rank adaptation (LoRA) and weight-decomposed low-rank adaptation (DoRA), have gained wide-spread interest. In this paper, we explore tradeoffs in parameter-efficient transfer learning using the synthetically pretrained Transformer-Based Optical Character recognition (TrOCR) model for handwritten text recognition with LoRA and DoRA. Additionally, we analyze the performance of full fine-tuning with a limited number of samples, scaling from a few-shot learning scenario up to using the whole dataset. We conduct experiments on the popular IAM Handwriting database as well as the historical READ 2016 dataset. We find that (a) LoRA/DoRA does not outperform full fine-tuning as opposed to a recent paper and (b) LoRA/DoRA is not substantially faster than full fine-tuning of TrOCR. © 2025 ieee.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning

Troika: Multi-Path Cross-Modal Traction for Compositional Ze...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Hu, Siteng Gong, Biao Feng, Yutong Zhang, Min Lv, Yiliang Wang, Donglin Zhejiang Univ Hangzhou Peoples R China Alibaba Grp Hangzhou Peoples R China Westlake Univ Sch Engn AI Div Machine Intelligence Lab MiLAB Hangzhou Peoples R China

ISBN: (纸本)9798350353006

Recent compositional zero-shot learning (CZSL) methods adapt pre-trained vision-language models (VLMs) by constructing trainable prompts only for composed state-object pairs. Relying on learning the joint representation of seen compositions, these methods ignore the explicit modeling of the state and object, thus limiting the exploitation of pre-trained knowledge and generalization to unseen compositions. With a particular focus on the universality of the solution, in this work, we propose a novel paradigm for CZSL models that establishes three identification branches (i.e., Multi-Path) to jointly model the state, object, and composition. The presented Troika is an outstanding implementation that aligns the branch-specific prompt representations with decomposed visual features. To calibrate the bias between semantically similar multi-modal representations, we further devise a Cross-Modal Traction module into Troika that shifts the prompt representation towards the current visual content. We conduct extensive experiments on three popular benchmarks, where our method significantly outperforms existing methods in both closed-world and open-world settings. The code will be available at https://***/bighuang624/Troika.

关键词： compositional zero-shot learning parameter-efficient transfer learning Troika vision-language models

来源：评论

学校读者我要写书评

暂无评论

Boosting Object Detection with Zero-Shot Day-Night Domain Adaptation

Boosting Object Detection with Zero-Shot Day-Night Domain Ad...

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Du, Zhipeng Shi, Miaojing Deng, Jiankang Kings Coll London Dept Informat London England Tongji Univ Coll Elect & Informat Engn Shanghai Peoples R China Imperial Coll London Dept Comp London England Huawei London Res London England

ISBN: (纸本)9798350353006

Detecting objects in low-light scenarios presents a persistent challenge, as detectors trained on well-lit data exhibit significant performance degradation on low-light data due to low visibility. Previous methods mitigate this issue by exploring image enhancement or object detection techniques with real low-light image datasets. However, the progress is impeded by the inherent difficulties about collecting and annotating low-light images. To address this challenge, we propose to boost low-light object detection with zero-shot day-night domain adaptation, which aims to generalize a detector from well-lit scenarios to low-light ones without requiring real low-light data. Revisiting Retinex theory in the low-level vision, we first design a reflectance representation learning module to learn Retinex-based illumination invariance in images with a carefully designed illumination invariance reinforcement strategy. Next, an interchange-redecomposition-coherence procedure is introduced to improve over the vanilla Retinex image decomposition process by performing two sequential image decompositions and introducing a redecomposition cohering loss. Extensive experiments on ExDark, DARK FACE, and CODaN datasets show strong low-light generalizability of our method. Our code is available at https://***/ZPDu/DAI-Net.

关键词： Low-light vision Object Detction Zero-shot Domain Adaptation

来源：评论

学校读者我要写书评

暂无评论

GenZI: Zero-Shot 3D Human-Scene Interaction Generation

GenZI: Zero-Shot 3D Human-Scene Interaction Generation

引用

ieee/cvf conference on computer vision and pattern recognition (CVPR)

作者： Li, Lei Dai, Angela Tech Univ Munich Munich Germany

ISBN: (纸本)9798350353006

Can we synthesize 3D humans interacting with scenes without learning from any 3D human-scene interaction data? We propose GenZI(1), the first zero-shot approach to generating 3D human-scene interactions. Key to GenZI is our distillation of interaction priors from large vision-language models (VLMs), which have learned a rich semantic space of 2D human-scene compositions. Given a natural language description and a coarse point location of the desired interaction in a 3D scene, we first leverage VLMs to imagine plausible 2D human interactions inpainted into multiple rendered views of the scene. We then formulate a robust iterative optimization to synthesize the pose and shape of a 3D human model in the scene, guided by consistency with the 2D interaction hypotheses. In contrast to existing learning-based approaches, GenZI circumvents the conventional need for captured 3D interaction data, and allows for flexible control of the 3D interaction synthesis with easy-to-use text prompts. Extensive experiments show that our zero-shot approach has high flexibility and generality, making it applicable to diverse scene types, including both indoor and outdoor environments.

关键词： Human-Scene Interaction vision-Language Models Zero-Shot

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共500页 << < 29 30 31 32 33 34 35 36 37 38 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：